Create Transcription

POST

audio

transcriptions

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["COMETAPI_KEY"],
    base_url="https://api.cometapi.com/v1"
)

audio_file = open("audio.mp3", "rb")
transcription = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file
)
print(transcription.text)

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: process.env.COMETAPI_KEY,
  baseURL: "https://api.cometapi.com/v1"
});

const transcription = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("audio.mp3")
});
console.log(transcription.text);

curl -X POST https://api.cometapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model="whisper-1" \
  -F file="@audio.mp3"

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cometapi.com/v1/audio/transcriptions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data; boundary=---011000010111000001101001"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.cometapi.com/v1/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.cometapi.com/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cometapi.com/v1/audio/transcriptions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "text": "Hello, welcome to CometAPI."
}

Usa este endpoint para transcribir audio a texto en el idioma de origen. Es adecuado para notas de reuniones, mensajes de voz, indexación de medios, subtítulos y flujos de trabajo de soporte que necesitan texto buscable.

Primera solicitud

Envía un archivo de audio compatible con model y file. Mantén el primer archivo corto mientras validas el manejo de cargas, la autenticación y el análisis de la respuesta.

Leer la respuesta

La respuesta predeterminada incluye el text transcrito. Si solicitas otro formato de respuesta, asegúrate de que tu cliente analice ese formato en lugar de asumir la estructura JSON predeterminada.

Próximos pasos

Usa Create Speech cuando necesites salida de texto a voz.
Usa Create Translation cuando la salida de destino deba ser en inglés.

Autorizaciones

Authorization

string

header

requerido

Bearer token authentication. Use your CometAPI key.

Cuerpo

multipart/form-data

file

requerido

The audio file to transcribe. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.

model

string

predeterminado:whisper-1

requerido

The speech-to-text model to use. Choose a current speech model from the Models page.

language

string

The language of the input audio in ISO-639-1 format (e.g., en, zh, ja). Supplying the language improves accuracy and latency.

prompt

string

Optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

response_format

enum<string>

predeterminado:json

The output format for the transcription.

Opciones disponibles:

json,

text,

srt,

verbose_json,

vtt

temperature

number

predeterminado:0

Sampling temperature between 0 and 1. Higher values produce more random output; lower values are more focused. When set to 0, the model auto-adjusts temperature using log probability.

Rango requerido: 0 <= x <= 1

Respuesta

200 - application/json

The transcription result.

text

string

requerido

The transcribed text.

Create Speech

Create Translation

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["COMETAPI_KEY"],
    base_url="https://api.cometapi.com/v1"
)

audio_file = open("audio.mp3", "rb")
transcription = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file
)
print(transcription.text)

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: process.env.COMETAPI_KEY,
  baseURL: "https://api.cometapi.com/v1"
});

const transcription = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("audio.mp3")
});
console.log(transcription.text);

curl -X POST https://api.cometapi.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -F model="whisper-1" \
  -F file="@audio.mp3"

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cometapi.com/v1/audio/transcriptions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data; boundary=---011000010111000001101001"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.cometapi.com/v1/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.cometapi.com/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cometapi.com/v1/audio/transcriptions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\nwhisper-1\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "text": "Hello, welcome to CometAPI."
}

Moderación de contenido

Claves API

Primera solicitud

Leer la respuesta

Próximos pasos

Autorizaciones

Cuerpo

Respuesta

​Primera solicitud

​Leer la respuesta

​Próximos pasos

Autorizaciones

Cuerpo

Respuesta

Primera solicitud

Leer la respuesta

Próximos pasos